A fuel cell diagnosis method and diagnosis system

Abstract

The invention provides a fuel cell diagnosis method and diagnosis system, including: injecting synchronous multi-frequency current excitation into the fuel cell; collecting the time domain current excitation signal and voltage feedback signal of the fuel cell, and calculating the AC current at different frequency points Impedance spectrum data; construct the AC impedance spectrum model of the fuel cell, and convert the nonlinear model equation of the AC impedance spectrum model into a linear model equation; fit the AC impedance spectrum data and the linear model equation according to the principle of least squares, and obtain the AC The parameter values ​​of the impedance spectrum model; the eigenvectors of the fuel cell are obtained according to the parameter values; the fault classification algorithm is used to classify the eigenvectors, and the working status of the fuel cell is diagnosed according to the classification results, thereby greatly reducing the calculation by fitting the linear model equation The complexity and amount of calculation, and also avoid the problem that the nonlinear least squares method is easy to fall into local optimum and low precision.

Description

technical field [0001] The present invention relates to the technical field of fuel cells, more specifically, to a fuel cell diagnosis method and a diagnosis system. Background technique [0002] A fuel cell is a device that converts chemical energy stored in fuel and oxidant into electrical energy through an electrochemical reaction. Although fuel cells have the advantages of low reaction temperature, fast dynamic response, high reaction efficiency, and high power density, they are prone to reaction starvation caused by insufficient gas supply and membrane dryness and water damage caused by improper water management during operation. Faults such as flooding, therefore, lead to the problems of short life and poor reliability of the fuel cell. [0003] In order to improve the reliability and service life of the fuel cell, it is necessary to diagnose and control the internal state of the fuel cell in real time. Since electrochemical impedance spectroscopy, also known as AC i...

AI Technical Summary

Problems solved by technology

However, this parameter determination method based on nonlinear least squares fitting has a large computational complexity and a large amount of computation, resulting in low diagnostic efficiency of the internal state of the fuel cell.

Images